A system for automatically generating user interest profiles and delivering information to users learns a user's interests by monitoring the user's outbound communication streams, i.e., the information that the user produces either by typing (e.g., while a user is composing an e-mail message or editing a word processor document) or by speaking (e.g., while a user is engaged in a phone conversation or listening to a lecture). The system uses the monitored text to build (and possibly update) a user interest profile. The profile is constructed from current text generated by the user, so that the retrieved information reflects present user interests. In addition, the profile may also retain past user interests, so that the profile reflects a combination of past and present user interests. The system then automatically queries diverse databases for information relevant to the interest profile. The databases may include internet web pages, files stored on the user's local network, and other local or remote data repositories. The queries may use a combination of internet search engines, the specific selection of which may depend upon the nature and/or content of the queries. The information retrieved in response to the queries is then presented to the user. The retrieved information may contain, for example, answers to questions that the user might ask and/or data related to the user's current and continuing interests. Because a user's current speech or typed text is highly correlated with the user's current interests, the retrieved information will be relevant to the user's actual interests. The communication stream monitoring, interest profile building, data base querying, and presentation of retrieved information are all performed automatically, in real time, and in the background of current user activities.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer-implemented method for determining an interest profile of a user based on the user's outbound communication streams, comprising: monitoring in real time a text information stream entered by the user of a computer application program comprising text editing functionality, wherein the text information is based on the user's outbound communication streams and wherein said text information is not a search query; extracting keywords from the text information, wherein the keywords are not defined by the user nor guided by the user; generating database queries from the keywords wherein the generation of database queries is not defined nor guided by the user; retrieving database information relevant to the queries; and presenting the database information to the user, wherein the database information is of interest to the user and based on the user's outbound communication streams; wherein the monitoring, generating, retrieving, and presenting are performed automatically and in the background while the computer application program is being used.
2. The method of claim 1 wherein the computer application program is an e-mail client application program.
3. The method of claim 2 wherein the text information stream comprises text content of e-mail message fields generated by the user while typing or speaking.
4. The method of claim 1 wherein the database queries are generated with formatting appropriate for multiple distinct databases.
5. The method of claim 1 further comprising submitting the database queries to web search engines, and wherein retrieving database information comprises receiving search results from the search engines.
6. The method of claim 1 wherein the database information comprises references to local documents.
7. The method of claim 1 wherein the database information comprises references to web documents.
8. The method of claim 1 wherein presenting the database information to the user comprises displaying to the user references to database documents.
9. The method of claim 1 further comprising automatically incorporating the database information into the application program.
10. A computer-implemented method for determining an interest profile of a user based on the user's outbound communication streams, comprising: monitoring in real time a text information stream entered by the user of a computer application program comprising text editing functionality, wherein the text information is based on the user's outbound communication streams and wherein said text information is not a search query; generating database queries from the text information wherein the generation of database queries is not defined nor guided by the user; calculating for each of the database queries a relevance vector, wherein each component of the relevance vector measures a relevance of the query to a predetermined category of a taxonomy tree; and computing the user interest profile from the relevance vectors calculated for the database queries; wherein the monitoring, generating, calculating, and computing are performed automatically and in the background while the computer application program is being used.
11. The method of claim 10 further comprising retrieving database information relevant to the profile; and presenting the database information to the user.
12. The method of claim 10 wherein computing the user interest profile comprises identifying long-term interests, identifying short-term interests, and forming a weighted combination of the long-term interests and the short-term interests such that long-term interests decrease in significance over time.
13. The method of claim 10 wherein computing the user interest profile comprises selecting the user interest profile from a database of potential profiles.
14. The method of claim 10 wherein generating database queries comprises extracting basic query units using a set of rules and a database of keywords, and forming key-tuples from the text information generated by the user.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
January 8, 1999
November 25, 2003
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.